Continual Learning with Adaptive Weights (CLAW)

Adel, T. , Zhao, H. and Turner, R. E. (2019) Continual Learning with Adaptive Weights (CLAW). In: ICLR 2020 Eighth International Conference on Learning Representations, Virtual Conference, Formerly Addis Ababa, Ethiopia, 26-30 April 2020,

Abstract

Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner. Recently, several frameworks have been developed which enable deep learning to be deployed in this learning scenario. A key modelling decision is to what extent the architecture should be shared across tasks. On the one hand, separately modelling each task avoids catastrophic forgetting but it does not support transfer learning and leads to large models. On the other hand, rigidly specifying a shared component and a task-specific part enables task transfer and limits the model size, but it is vulnerable to catastrophic forgetting and restricts the form of task-transfer that can occur. Ideally, the network should adaptively identify which parts of the network to share in a data driven way. Here we introduce such an approach called Continual Learning with Adaptive Weights (CLAW), which is based on probabilistic modelling and variational inference. Experiments show that CLAW achieves state-of-the-art performance on six benchmarks in terms of overall continual learning performance, as measured by classification accuracy, and in terms of addressing catastrophic forgetting.

• Item Type: Conference Proceedings
• Additional Information: HZ acknowledges support from the DARPA XAI project, contract#FA87501720152 and an Nvidia GPU grant. RT acknowledges support by Google, Amazon, Improbable and EPSRC grants EP/M0269571 and EP/L000776/1.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Hesham, Dr Tameem Adel
• Authors: Adel, T., Zhao, H., and Turner, R. E.
• College/School: College of Science and Engineering > School of Computing Science
• Copyright Holders: Copyright © 2020 The Authors
• Publisher Policy: Reproduced with the permission of the publisher

Related URLs

• Organisation
• Publisher